crates/clawhdf5-agent/src/consolidation.rs

@@ -16,6 +16,55 @@ pub enum MemorySource {
     Correction,
 }
 
+/// Source classification for content whose true origin is *not*
+/// independently verified by the caller of [`ConsolidationEngine::add_memory`]
+/// — arbitrary text forwarded from a user, a tool's output, or a retrieval
+/// pipeline. This is the only source set `add_memory` accepts; it cannot
+/// claim the `System`/`Correction` importance boost (see [`TrustedSource`]
+/// and [`ConsolidationEngine::add_trusted_memory`]) — a caller passing
+/// through untrusted content has no way to self-report an elevated trust
+/// level through this entry point.
+#[derive(Clone, Debug, PartialEq)]
+pub enum UntrustedSource {
+    User,
+    Tool,
+    Retrieval,
+}
+
+impl From<UntrustedSource> for MemorySource {
+    fn from(s: UntrustedSource) -> Self {
+        match s {
+            UntrustedSource::User => MemorySource::User,
+            UntrustedSource::Tool => MemorySource::Tool,
+            UntrustedSource::Retrieval => MemorySource::Retrieval,
+        }
+    }
+}
+
+/// Source classification for content whose elevated trust level has been
+/// independently verified by the caller — e.g. the library's own
+/// system-generated text, or a caller that ran its own correction-cue
+/// detection (as `memory_strategy::SaveOnUserCorrection` does) rather than
+/// forwarding a caller-supplied label verbatim. `MemorySource::System`/
+/// `Correction` get elevated importance weighting in
+/// [`ImportanceScorer::score_correction`]; only reachable through
+/// [`ConsolidationEngine::add_trusted_memory`], a distinct entry point from
+/// the one untrusted content is passed through.
+#[derive(Clone, Debug, PartialEq)]
+pub enum TrustedSource {
+    System,
+    Correction,
+}
+
+impl From<TrustedSource> for MemorySource {
+    fn from(s: TrustedSource) -> Self {
+        match s {
+            TrustedSource::System => MemorySource::System,
+            TrustedSource::Correction => MemorySource::Correction,
+        }
+    }
+}
+
 #[derive(Clone, Debug, PartialEq)]
 pub enum MemoryTier {
     Working,
@@ -199,10 +248,41 @@ impl ConsolidationEngine {
         }
     }
 
-    /// Add a new memory to the Working tier.
+    /// Add a new memory to the Working tier from an untrusted/ordinary origin
+    /// (User, Tool, or Retrieval). This is the entry point for arbitrary
+    /// caller-supplied content — it cannot claim the elevated System/
+    /// Correction importance boost. Use [`Self::add_trusted_memory`] for
+    /// content whose elevated trust level the caller has independently
+    /// verified.
     ///
     /// Importance is scored against existing Working-tier records only.
     pub fn add_memory(
+        &mut self,
+        chunk: String,
+        embedding: Vec<f32>,
+        source: UntrustedSource,
+        now: f64,
+    ) -> u64 {
+        self.add_memory_with_source(chunk, embedding, source.into(), now)
+    }
+
+    /// Add a new memory tagged System or Correction, which get elevated
+    /// importance weighting in [`ImportanceScorer::score_correction`]. Only
+    /// call this from code that has independently verified the origin (the
+    /// library's own system-generated text, or a caller that ran its own
+    /// correction-cue detection) — never from a path that forwards a
+    /// caller-supplied trust label verbatim.
+    pub fn add_trusted_memory(
+        &mut self,
+        chunk: String,
+        embedding: Vec<f32>,
+        source: TrustedSource,
+        now: f64,
+    ) -> u64 {
+        self.add_memory_with_source(chunk, embedding, source.into(), now)
+    }
+
+    fn add_memory_with_source(
         &mut self,
         chunk: String,
         embedding: Vec<f32>,
@@ -418,13 +498,44 @@ mod tests {
     // ---------------------------------------------------------------------------
     // 2. Add memory — basic
     // ---------------------------------------------------------------------------
+    /// add_trusted_memory(TrustedSource::Correction) must actually produce a
+    /// MemorySource::Correction record — the only way to reach that elevated
+    /// classification, since add_memory's UntrustedSource has no such variant.
+    #[test]
+    fn test_add_trusted_memory_sets_correction_source() {
+        let mut engine = ConsolidationEngine::new(ConsolidationConfig::default());
+        let id = engine.add_trusted_memory(
+            "verified correction".to_string(),
+            unit_vec(4, 0),
+            TrustedSource::Correction,
+            0.0,
+        );
+        let rec = engine.get_by_id(id).unwrap();
+        assert_eq!(rec.source, MemorySource::Correction);
+    }
+
+    /// add_trusted_memory(TrustedSource::System) must produce a
+    /// MemorySource::System record.
+    #[test]
+    fn test_add_trusted_memory_sets_system_source() {
+        let mut engine = ConsolidationEngine::new(ConsolidationConfig::default());
+        let id = engine.add_trusted_memory(
+            "bootstrap text".to_string(),
+            unit_vec(4, 0),
+            TrustedSource::System,
+            0.0,
+        );
+        let rec = engine.get_by_id(id).unwrap();
+        assert_eq!(rec.source, MemorySource::System);
+    }
+
     #[test]
     fn test_add_memory_basic() {
         let mut engine = ConsolidationEngine::new(ConsolidationConfig::default());
         let id = engine.add_memory(
             "Hello world".to_string(),
             unit_vec(4, 0),
-            MemorySource::User,
+            UntrustedSource::User,
             1_000_000.0,
         );
         assert_eq!(id, 0);
@@ -592,7 +703,7 @@ mod tests {
             let id = engine.add_memory(
                 "x".to_string(),
                 unit_vec(4, i as usize),
-                MemorySource::User,
+                UntrustedSource::User,
                 i as f64,
             );
             // Force low importance so promotion threshold is not crossed.
@@ -625,10 +736,10 @@ mod tests {
         let cfg = ConsolidationConfig::default();
         let mut engine = ConsolidationEngine::new(cfg);
 
-        let id = engine.add_memory(
+        let id = engine.add_trusted_memory(
             "important memory".to_string(),
             unit_vec(4, 0),
-            MemorySource::Correction,
+            TrustedSource::Correction,
             0.0,
         );
         // Force importance above threshold.
@@ -661,7 +772,7 @@ mod tests {
         let id = engine.add_memory(
             "frequently accessed".to_string(),
             unit_vec(4, 0),
-            MemorySource::User,
+            UntrustedSource::User,
             0.0,
         );
 
@@ -689,7 +800,7 @@ mod tests {
     #[test]
     fn test_access_memory_reactivation() {
         let mut engine = ConsolidationEngine::new(ConsolidationConfig::default());
-        let id = engine.add_memory("chunk".to_string(), unit_vec(4, 0), MemorySource::User, 0.0);
+        let id = engine.add_memory("chunk".to_string(), unit_vec(4, 0), UntrustedSource::User, 0.0);
 
         engine.access_memory(id, 5000.0);
         let rec = engine.get_by_id(id).unwrap();
@@ -710,11 +821,11 @@ mod tests {
         let mut engine = ConsolidationEngine::new(ConsolidationConfig::default());
 
         // 2 Working
-        engine.add_memory("w1".to_string(), unit_vec(4, 0), MemorySource::User, 0.0);
-        engine.add_memory("w2".to_string(), unit_vec(4, 1), MemorySource::User, 0.0);
+        engine.add_memory("w1".to_string(), unit_vec(4, 0), UntrustedSource::User, 0.0);
+        engine.add_memory("w2".to_string(), unit_vec(4, 1), UntrustedSource::User, 0.0);
 
         // 1 Episodic (manually set)
-        let id_e = engine.add_memory("e1".to_string(), unit_vec(4, 2), MemorySource::User, 0.0);
+        let id_e = engine.add_memory("e1".to_string(), unit_vec(4, 2), UntrustedSource::User, 0.0);
         engine
             .records
             .iter_mut()
@@ -723,7 +834,7 @@ mod tests {
             .tier = MemoryTier::Episodic;
 
         // 1 Semantic (manually set)
-        let id_s = engine.add_memory("s1".to_string(), unit_vec(4, 3), MemorySource::User, 0.0);
+        let id_s = engine.add_memory("s1".to_string(), unit_vec(4, 3), UntrustedSource::User, 0.0);
         engine
             .records
             .iter_mut()
@@ -752,7 +863,7 @@ mod tests {
             let id = engine.add_memory(
                 "episodic chunk".to_string(),
                 unit_vec(4, i as usize),
-                MemorySource::User,
+                UntrustedSource::User,
                 i as f64,
             );
             let rec = engine.records.iter_mut().find(|r| r.id == id).unwrap();

crates/clawhdf5-agent/src/lib.rs

@@ -349,18 +349,24 @@ impl HDF5Memory {
     // ---- Provenance & anomaly detection ------------------------------------
     //
     // Heuristic, best-effort session bookkeeping: a coarse MemorySource
-    // inferred from the caller-supplied source_channel string (not a trust
-    // boundary — see consolidation::MemorySource for the gated construction
-    // path), a content hash per record for detecting accidental in-session
-    // corruption, and write-pattern anomaly checks (rate, injection-pattern,
+    // inferred from the caller-supplied source_channel string, a content
+    // hash per record for detecting accidental in-session corruption, and
+    // write-pattern anomaly checks (rate, injection-pattern,
     // source-distribution skew) run on every save/update.
 
     /// Infer a coarse `MemorySource` from a free-text `source_channel` for
     /// provenance/anomaly bookkeeping purposes only.
+    ///
+    /// `source_channel` is caller-supplied and unvalidated (`MemoryEntry` has
+    /// no trust field), so this deliberately never returns `System` or
+    /// `Correction` — those are consolidation::MemorySource's elevated
+    /// classifications (see `UntrustedSource`/`TrustedSource`), and inferring
+    /// them from a string the caller controls would let a write dodge
+    /// `check_source_anomaly`'s User-flood detection by simply labeling
+    /// itself `source_channel = "system"`. Everything not recognized as
+    /// `Tool`/`Retrieval` is conservatively bucketed as `User`.
     fn infer_memory_source(source_channel: &str) -> consolidation::MemorySource {
         match source_channel {
-            "correction" => consolidation::MemorySource::Correction,
-            "system" => consolidation::MemorySource::System,
             "tool" => consolidation::MemorySource::Tool,
             "retrieval" => consolidation::MemorySource::Retrieval,
             _ => consolidation::MemorySource::User,
@@ -909,6 +915,33 @@ mod tests {
         assert!(!mem.provenance.verify_integrity(idx as u64, "tampered"));
     }
 
+    /// A caller cannot dodge check_source_anomaly's User-flood detection by
+    /// self-labeling source_channel = "system" — infer_memory_source must
+    /// never grant the elevated System/Correction classification from
+    /// unvalidated caller-supplied text.
+    #[test]
+    fn source_channel_cannot_claim_system_to_evade_source_anomaly() {
+        let dir = TempDir::new().unwrap();
+        let config = make_config(&dir);
+        let mut mem = HDF5Memory::create(config).unwrap();
+
+        for i in 0..15 {
+            let mut entry = make_entry(&format!("flood {i}"), &[1.0, 0.0, 0.0, 0.0]);
+            entry.source_channel = "system".to_owned();
+            entry.timestamp = 1000000.0 + i as f64;
+            mem.save(entry).unwrap();
+        }
+
+        let alerts = mem.take_anomaly_alerts();
+        assert!(
+            alerts
+                .iter()
+                .any(|a| a.message.contains("source distribution")),
+            "a flood of writes claiming source_channel=\"system\" must still trigger \
+             source-distribution anomaly detection as User-sourced, got: {alerts:?}"
+        );
+    }
+
     /// A chunk containing a known injection pattern must raise a queued
     /// anomaly alert through the real save path, not just in anomaly.rs's
     /// own unit tests.

crates/clawhdf5-bench/src/bin/consolidation_efficiency.rs

@@ -22,7 +22,9 @@
 use std::time::Instant;
 
 use clawhdf5_agent::bm25::BM25Index;
-use clawhdf5_agent::consolidation::{ConsolidationConfig, ConsolidationEngine, MemorySource};
+use clawhdf5_agent::consolidation::{
+    ConsolidationConfig, ConsolidationEngine, TrustedSource, UntrustedSource,
+};
 use clawhdf5_agent::hybrid::hybrid_search;
 
 const EMBEDDING_DIM: usize = 384;
@@ -232,7 +234,7 @@ fn run_quality_benchmark() {
     for i in 0..SIGNAL_KEYWORDS.len() {
         let chunk = make_signal_content(i);
         let embedding = make_embedding(i * 1000);
-        let id = engine.add_memory(chunk, embedding, MemorySource::Correction, now);
+        let id = engine.add_trusted_memory(chunk, embedding, TrustedSource::Correction, now);
         signal_ids.push(id);
     }
 
@@ -240,7 +242,7 @@ fn run_quality_benchmark() {
     for i in 0..990 {
         let chunk = make_noise_content(i);
         let embedding = make_embedding(i + 100);
-        engine.add_memory(chunk, embedding, MemorySource::System, now + i as f64 * 0.1);
+        engine.add_trusted_memory(chunk, embedding, TrustedSource::System, now + i as f64 * 0.1);
     }
 
     println!("  → Inserted {} records total", engine.records().len());
@@ -333,7 +335,7 @@ fn run_cycle_time_benchmark() {
         for i in 0..n {
             let chunk = make_noise_content(i);
             let embedding = make_embedding(i);
-            engine.add_memory(chunk, embedding, MemorySource::User, now + i as f64);
+            engine.add_memory(chunk, embedding, UntrustedSource::User, now + i as f64);
         }
 
         // Warmup
@@ -344,7 +346,7 @@ fn run_cycle_time_benchmark() {
         for i in n..(n * 2) {
             let chunk = make_noise_content(i);
             let embedding = make_embedding(i);
-            engine.add_memory(chunk, embedding, MemorySource::User, now + i as f64);
+            engine.add_memory(chunk, embedding, UntrustedSource::User, now + i as f64);
         }
 
         // Timed consolidation
@@ -410,13 +412,13 @@ fn run_memory_reduction_benchmark() {
         for i in 0..signal_count {
             let chunk = make_signal_content(i % SIGNAL_KEYWORDS.len());
             let emb = make_embedding(i * 999);
-            let id = engine.add_memory(chunk, emb, MemorySource::Correction, now);
+            let id = engine.add_trusted_memory(chunk, emb, TrustedSource::Correction, now);
             signal_ids.push(id);
         }
         for i in 0..noise_count {
             let chunk = make_noise_content(i);
             let emb = make_embedding(i + 200);
-            engine.add_memory(chunk, emb, MemorySource::System, now + i as f64 * 0.1);
+            engine.add_trusted_memory(chunk, emb, TrustedSource::System, now + i as f64 * 0.1);
         }
 
         // Access signal records heavily